args['trimRead2'] = os.path.join(args['fastqSampleDir'],
args['name'] + '_trim_R2.fastq.gz')
args['trimLog'] = os.path.join(args['fastqSampleDir'],
args['name'] + '_trim.log')
args['qcLog'] = os.path.join(args['fastqSampleDir'], args['name'] + '_qc.log')
# Generate commands to process single-end FASTQ files
if args['--singleend']:
# Create trim command
trimReadsCommand = fastqTrim.cutadaptTrim(readIn=args['read1'],
readOut=args['trimRead1'],
path=paths['cutadapt'],
length=args['--minlength'],
quality=args['--trimqual'])
# Create QC command
fastqcCommand = fastqQC.fastQC(inFile=args['trimRead1'],
outDir=args['fastqSampleDir'],
path=paths['fastqc'])
# Empty read2 file
args['trimRead2'] = None
# Generate commands to process paired-end FASTQ files
else:
# Create trim command
trimReadsCommand = fastqTrim.cutadaptTrimPaired(read1In=args['read1'],
read2In=args['read2'],
read1Out=args['trimRead1'],
read2Out=args['trimRead2'],
path=paths['cutadapt'],
length=args['--minlength'],
quality=args['--trimqual'])
# Generate QC command
read1Fastqc = fastqQC.fastQC(inFile=args['trimRead1'],
args['qcLog'] = os.path.join(args['fastqSampleDir'],
args['name'] + '_qc.log')
# Generate commands to process single-end FASTQ files
if args['--singleend']:
# Create trim command
trimReadsCommand = fastqTrim.cutadaptTrim(
readIn = args['read1'],
readOut = args['trimRead1'],
path = paths['cutadapt'],
length = args['--minlength'],
quality = args['--trimqual']
)
# Create QC command
fastqcCommand = fastqQC.fastQC(
inFile = args['trimRead1'],
outDir = args['fastqSampleDir'],
path = paths['fastqc']
)
# Empty read2 file
args['trimRead2'] = None
# Generate commands to process paired-end FASTQ files
else:
# Create trim command
trimReadsCommand = fastqTrim.cutadaptTrimPaired(
read1In = args['read1'],
read2In = args['read2'],
read1Out = args['trimRead1'],
read2Out = args['trimRead2'],
path = paths['cutadapt'],
length = args['--minlength'],
quality = args['--trimqual']
###############################################################################
## Generate commands to perform fastqc
###############################################################################
# Generate log file name
args['qcLog'] = os.path.join(args['fastqSampleDir'],
args['name'] + '_fastqc.log')
# Create fastqc command
fastqcCommand = []
for fastq in (args['trimRead1'], args['trimRead2']):
if fastq is None:
continue
fastqcCommand.append(
fastqQC.fastQC(
inFile = fastq,
outDir = args['fastqSampleDir'],
path = pmDict[('fastqc', 'path')]
)
)
fastqcCommand = '; '.join(fastqcCommand)
# Submit FASTQC commands
fastqcJobID = slurmJobs.add(
command = fastqcCommand,
stdout = args['qcLog'],
stderr = args['qcLog'],
depend = [trimReadsJobID],
modules = pmDict[('fastqc', 'modules')]
)
###############################################################################
## Generate RSEM Transcript alignment command
read2Out=trim2,
quality=0,
adapter=args['--trim'],
length=25,
path=pmDict[('cutadapt', 'path')])
trimJobID = slurmJobs.add(trimCommand,
processors=1,
memory=6,
stdout=logFile,
stderr=logFile,
modules=pmDict[('cutadapt', 'modules')])
trimJobList.append(trimJobID)
# Create fastqc command
qcLog = args['<logprefix>'] + '.fastqc{}.log'.format(count)
qcCommand = fastqQC.fastQC(inFile=trim1,
outDir=args['<logfolder>'],
path=pmDict[('fastqc', 'path')])
if trim2:
qcCommand += ' && {}'.format(
fastqQC.fastQC(inFile=trim2,
outDir=args['<logfolder>'],
path=pmDict[('fastqc', 'path')]))
qcJobID = slurmJobs.add(qcCommand,
processors=1,
memory=6,
stdout=qcLog,
stderr=qcLog,
modules=pmDict[('fastqc', 'modules')],
depend=[trimJobID])
qcJobList.append(qcJobID)
# Switch input file names
moabJobs = moab.moabJobs()
# Create trim command and add to job dictionary
trimCommand = fastqTrim.cutadaptTrimPaired(read1In=args['read1'],
read2In=args['read2'],
read1Out=args['trmRd1'],
read2Out=args['trmRd2'],
path=paths['cutadapt'],
length=25,
quality=20,
adapter='CTGTCTCTTATACACATCT')
trimCommandID = moabJobs.add(trimCommand,
stdout=args['trmLog'],
stderr=args['trmLog'])
# Generate QC commands
read1Fastqc = fastqQC.fastQC(inFile=args['trmRd1'],
outDir=args['smpFsq'],
path=paths['fastqc'])
read2Fastqc = fastqQC.fastQC(inFile=args['trmRd2'],
outDir=args['smpFsq'],
path=paths['fastqc'])
# Combine FASTQ QC command and add to job dictionary
fastqcCommand = '%s && %s' % (read1Fastqc, read2Fastqc)
fastqcCommandID = moabJobs.add(fastqcCommand,
stdout=args['fqcLog'],
stderr=args['fqcLog'],
dependency=[trimCommandID])
# Generate command to perform alignment and add to job dictionary
alignCommand = fastqAlign.bowtie2Align(index=args['<bwt2index>'],
outFile=args['alnBam'],
read1=args['read1'],
read2=args['read2'],
###############################################################################
## Generate commands to perform fastqc
###############################################################################
# Generate log file name
args['qcLog'] = os.path.join(args['fastqSampleDir'],
args['name'] + '_fastqc.log')
# Create fastqc command
fastqcCommand = []
for fastq in (args['trimRead1'], args['trimRead2']):
if fastq is None:
continue
fastqcCommand.append(
fastqQC.fastQC(
inFile = fastq,
outDir = args['fastqSampleDir'],
path = pmDict[('fastqc', 'path')]
)
)
fastqcCommand = '; '.join(fastqcCommand)
# Submit FASTQC commands
fastqcJobID = slurmJobs.add(
command = fastqcCommand,
stdout = args['qcLog'],
stderr = args['qcLog'],
depend = [trimReadsJobID],
modules = pmDict[('fastqc', 'modules')]
)
###############################################################################
## Generate RSEM Transcript alignment command
